4 基于概率论的分类方法：朴素贝叶斯（三）

4.7 示例：使用朴素贝叶斯分类器从个人广告中获取区域倾向

前面介绍了两个应用：1.过滤网站的恶意留言；2.过滤垃圾邮件。

4.7.1 收集数据：导入RSS源

Universal Feed Parser是Python中最常用的RSS程序库。

在Python提示符下输入：

构建类似于spamTest()函数来对测试过程自动化。

#RSS源分类器及高频词去除函数
def calcMostFreg(vocabList, fullText):
    import operator
    freqDict = {}
    for token in vocabList:#遍历词汇表中的每个词，统计它在文本中出现的次数
        freqDict[token] = fullText.count(token)
    sortedFreq = sorted(freqDict.iteritems(), key = operator.itemgetter(1), reverse = True)
    return sortedFreq[:30]#返回排序最高的30个单词

def localWords(feed1, feed0):
    import feedparser
    docList = []; classList = []; fullText = []
    minLen = min(len(feed1['entries']), len(feed0['entries']))
    for i in range(minLen):#每次访问一条RSS源
        wordList = textParse(feed1['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)
    #去掉出现次数最高的那些词
    top30Words = calcMostFreg(vocabList, fullText)
    for pairW in top30Words:
        if pairW[0] in vocabList: vocabList.remove(pairW[0])

    trainingSet = range(2 * minLen); testSet = []
    for i in range(20):#随机抽取20个文件作为testSet
        randIndex = int(random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])
    trainMat = []; trainClasses = []
    for docIndex in trainingSet:
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses))
    errorCount = 0
    for docIndex in testSet:
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
    print 'the error rate is: ', float(errorCount)/len(testSet)
    return vocabList, p0V, p1V

4.7.2 分析数据：显示地域相关的用词

#最具表特征的词汇显示函数
def getTopWords(ny, sf):
    import operator
    vocabList, p0V, p1V = locablWords(ny, sf)
    topNY = []; topSF = []#创建列表用于元祖的存储
    for i in range(len(p0V)):
        if p0V[i] > -6.0：topSF.append((vocabList[i], p0V[i]))
        if p1V[i] > -6.0：topNY.append((vocabList[i], p1V[i]))
    sortedSF = sorted(topSF, key = lambda pair: pair[1], reverse = True)
    print "SF**SF**SF**SF**SF**SF**SF**SF**"
    for item in sortedSF:
        print item[0]
    sortedNY = sorted(topNY, key = lambda pair: pair[1], reverse = True)
    print "NY**NY**NY**NY**NY**NY**NY**NY**"
    for item in sortedNY:
        print item[0]